4 papers
Solving Jigsaw Puzzles in the Wild: Human-Guided Reconstruction of Cultural Heritage Fragments
Omidreza Safaei, Sinem Aslan, Sebastiano Vascon +3
Reassembling real-world archaeological artifacts from fragmented pieces poses significant challenges due to erosion, missing regions, irregular shapes, and large-scale ambiguity. T…
Machine-learned global glacier ice volumes
N. Maffezzoli, E. Rignot, C. Barbante +3
We present a global dataset of glacier ice thickness modeled with IceBoost v2.0, a machine learning model trained on 7 million ice thickness measurements and informed by physical a…
ECAM: A Contrastive Learning Approach to Avoid Environmental Collision in Trajectory Forecasting
Giacomo Rosin, Muhammad Rameez Ur Rahman, Sebastiano Vascon
Human trajectory forecasting is crucial in applications such as autonomous driving, robotics and surveillance. Accurate forecasting requires models to consider various factors, inc…
Backdoor Learning Curves: Explaining Backdoor Poisoning Beyond Influence Functions
Antonio Emanuele CinÃ, Kathrin Grosse, Sebastiano Vascon +4
Backdoor attacks inject poisoning samples during training, with the goal of forcing a machine learning model to output an attacker-chosen class when presented a specific trigger at…